Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical issues or problems

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "trouble" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oliberal
    -0.69
    VO
    -0.60
    urse
    -0.59
    ortium
    -0.58
     Parm
    -0.57
    ulture
    -0.56
    Revolution
    -0.55
    ird
    -0.55
    ECD
    -0.55
     lean
    -0.54
    POSITIVE LOGITS
    hooting
    1.49
    makers
    1.19
    maker
    1.02
    some
    0.95
    engers
    0.83
    ome
    0.79
    neck
    0.77
     brewing
    0.77
     aver
    0.72
    vable
    0.72
    Act Density 0.079%

    No Known Activations